Return a suggested next activity based on recent progress. No-op with a friendly canned reply for guest sessions.
AI agents call maker_next_suggestion to retrieve information from Crow without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool queries project memory/history to generate a suggestion, which is a retrieval operation. It has no capability to create, modify, delete, or execute external operations. The severity is low because even if misused, it only returns suggestions and cannot cause data loss, unwanted modifications, or external operations. High confidence due to clear descriptive language indicating read-only behavior.
From the tool's definition Tool 'returns a suggested next activity based on recent progress' — a read-only query that retrieves or derives data from project state without modifying anything.
Documented attack patterns abuse exactly the kind of access maker_next_suggestion gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and Crow, and nothing reaches the server without passing your rules. This is the rule we recommend for maker_next_suggestion:
{
"version": "1",
"default": "deny",
"tools": {
"maker_next_suggestion": {}
}
} maker_next_suggestion is read-only, so it stays allowed — but everything else on the server is denied unless you say otherwise.
Free to start. No card required.
Return a suggested next activity based on recent progress. No-op with a friendly canned reply for guest sessions. It is categorised as a Read tool in the Crow MCP Server, which means it retrieves data without modifying state.
Register the Crow MCP server in PolicyLayer and add a rule for maker_next_suggestion: allow, deny, rate-limit, or require approval. Point your MCP client at the PolicyLayer proxy URL and the rule is enforced on every call, before it reaches Crow. Nothing to install.
maker_next_suggestion is a Read tool with low risk. Read-only tools are generally safe to allow by default.
Yes. Add a rate_limit block to the maker_next_suggestion rule in your PolicyLayer policy. For example, setting max: 10 and window: 60 limits the tool to 10 calls per minute. Rate limits are tracked per agent session and reset automatically.
Set action: deny in the PolicyLayer policy for maker_next_suggestion. The AI agent will receive a policy violation error and cannot call the tool. You can also include a reason field to explain why the tool is blocked.
maker_next_suggestion is provided by the Crow MCP server (kh0pper/crow). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from Crow, add the rest of your stack, and see everything your agents can call. Then put policy on all of it.
Free to start. No card required.
576 Crow tools catalogued and risk-classified — across an index of 43,000+ MCP servers.